International Journal of Information Technology最新文献

Reducing the power quality problems and regulating the output DC voltage are considered as the essential problems need to be addressed for ensuring the increased performance of grid-PV systems. Different converter topologies and controlling strategies have been developed for this purpose in conventional works, but they are constrained by the major issues of increased computation complexity, high output error, harmonic distortions, and decreased voltage gain. Hence, this research work objects to develop a novel Mutated Ant Province Optimization (MAPO) algorithm incorporated with the modified SEPIC DC-DC converter techniques for solving the regulating the output voltage with reduced harmonics. In order to maximize the power output from the solar PV systems, the Perturb & Observe (P&O) Maximum Peak Point Tracking (MPPT) controlling technique is developed. Subsequently, the photovoltaic (PV) output voltage exhibits a stochastic behavior, necessitating effective regulation to enhance the output gain. The modified SEPIC DC-DC converter is employed for this specific objective, since it effectively adjusts the output voltage with minimized harmonics. However, the performance of the converter is solely dependent on the controller, as it generates controlling signals by optimally selecting parameters. Also, the switching components used in the converter circuit are operated based on the controlling signals. During simulations, Various measurements are used to validate and compare the effectiveness of the suggested converter and controlling mechanisms.

As Flying Ad Hoc Networks (FANETs) continue to advance, ensuring robust security, privacy, and data reliability remains a significant challenge. This research presents a novel framework known as HE-FSMF-short for Homomorphic Encrypted Federated Secure Matrix Factorization-specifically designed to tackle these challenges. HE-FSMF integrates matrix factorization with federated learning and homomorphic encryption to enhance both security and efficiency in FANET environments. Matrix factorization, commonly used in recommendation systems, is adapted here to address the unique complexities of FANETs. By leveraging detailed feature extraction through the VGG-16 model, HE-FSMF ensures precise and secure data processing even in dynamic and high-mobility settings. The incorporation of homomorphic encryption protects data throughout cloud-based computations, maintaining privacy and integrity without compromising performance. Additionally, HE-FSMF features mechanisms to verify the accuracy and authenticity of results, which is crucial for establishing trust in distributed systems. This framework not only enhances learning efficiency and improves data transmission rates but also provides strong safeguards for sensitive information. HE-FSMF offers a robust solution for advancing FANET capabilities, making it a valuable tool for secure and efficient communication in the increasingly interconnected and rapidly evolving landscape of networked systems.

Vehicular Ad-Hoc Networks (VANETs) are studied wireless networks that enable communication among vehicles and roadside infrastructure. The role a vital play in improving on-road safety, efficacy, and convenience by enabling real-time data interchange for controlling traffic, infotainment services, and collision avoidance. Energy efficiency in VANETs is vital because of the restricted power resources of vehicles. Methods like clustering, vehicles are categorized into groups to decrease communication overhead, and meta-heuristic approaches that optimize network performance by intelligent problem-solving approaches are deployed to exploit energy efficiency while preserving network reliability and responsiveness. These methodologies contribute to the effective implementation of VANETs, ensuring sustainable and dependable communication in dynamic vehicular environments. In this study, a new Squid Game Optimization based Energy Aware Clustering Approach (SGO-EACA) technique for VANET is introduced. The goal of the SGO-EACA technique is to optimally choose the cluster heads (CHs) and produce clusters in the VANET in such a way as to realize energy efficiency. In the SGO-EACA technique, the concept of typical Korean sport is used where the attackers try to achieve their goal, but players try to eliminate each other. Moreover, the SGO-EACA approach derives a fitness function (FF) containing multiple metrics such as Residual Energy (RE), Trust Level, Degree Difference, Total Energy consumption, Distance to Base Station (DBS), and Mobility. The simulation values exposed that the SGO-EACA approach surpassed earlier state-of-the-art approaches with respect to various aspects.

In this study, we developed a variant of the support vector machine (SVM) neural classifier and utilized it to categorize clans in a genealogical dataset. For each of the five kernels, all four variants, twin SVM (TSVM), proximal SVM (PSVM), twin proximal SVM (TPSVM), and multi-class SVM (MCSVM) classifier are simulated and tested. The analysis of variance - radial basis function (ANOVA RBF) kernel outperformed all other SVM variants, in terms of classification accuracy with the lowest error value. Additionally, it is found that for the considered dataset, TPSVM neural classifier with ANOVA RBF Kernel generated 98.91% classification accuracy, and the TPSVM classifier has achieved the minimized mean square error (MSE) value of 0.00015. The Twin Proximal SVM classifier has produced enhanced classification accuracy with better precision and F1-score in comparison to all other developed and simulated SVM classifier models.

The article presents a methodology for generating a simulation Simulink model of a rocket. The use of the MATLAB/Simulink environment for simulating the flight of a rocket and calculating its aerodynamic characteristics is described in detail. The principles of forming blocks for calculating the parameters of a standard atmosphere, aerodynamic characteristics, power plant thrust, flight angles, altitude and flight range are described. The results of numerical experiments carried out using the MATLAB/Simulink environment are presented.

In the agricultural supply and food, chain Ensuring product safety is important which includes monitoring the effective logistics management and advancements of agricultural products. An effective model that guarantees sufficient safety of the product is required because many issues have been raised regarding contamination risks and food safety. Thus, an efficacious model is introduced in this article referred to as Blockchain Based-Crossover Young’s double-slit (BC-CYD) algorithm, which enables securing agriculture-based data in supply chain management. The developed approach successfully executes the transactions in the traceability and tracking of products with high-level security for the agricultural supply chain. The developed method utilizes an authentication process in provenance tracking and product information storage. The developed BC-CYD method improves safety and efficiency by obtaining higher security, reliability, and integrity. Here, product transactions are stored in the blockchain ledger, thereby, the developed model offers high-level traceability and transparency in a capable manner in the supply chain management. The effectiveness of the proposed BC-CYD method is assayed, where evaluation parameters quantify the efficiency of the developed BC-CYD method. Based on the performance rates of Precision, ROC, accuracy, and Processing time, the developed BC-CYD method’s effectiveness is ascertained as higher. The suggested BC-CYD method yields a greater precision of 97.4% and its accuracy is 98.8% with lower processing time and training time.

Network coverage plays an indispensable role in determining the Heterogeneous Wireless Sensor Networks (HWSNs) potentiality towards the process of monitoring the physical world with maximized service quality. This HWSNs possesses the limitations of complex deployment environments, poor node reliability and restricted energy which directly influences the transmission and data collection process of sensor nodes and minimizes the network performance. An efficient network coverage controlling mechanism need to be devised and implemented for improving the network service quality, lifetime, reducing energy consumption, and achieve rational utilization of limited resources. In this paper, a Hybrid Sand Cat Swarm Optimization Algorithm-based Reliable Coverage Optimization Strategy (HSCOARCS) is proposed for preventing the issue of coverage redundancy and coverage blind areas, and maximally optimize the sensor node deployment location to achieve reliable sensing and monitoring of target area. This proposed HSCOARCS is implemented over a HWSN coverage mathematical model which represents a problem of combinatorial optimization. The hybridization of Sand Cat Swarm Optimization Algorithm (SCSOA) is achieved for enhancing the speed of the global convergence with the initial population achieved using the method of Gaussian distribution. It targets on the optimization objectives that aids in minimizing the network costs and improve its coverage. The simulation results of the proposed HSSCSOA confirmed better network reliability of 21.38%, network coverage of 19.76%, and minimized energy consumption of 17.92% with different number of sensor nodes on par with the benchmarked schemes used for comparison.

To build a Cancer prediction model based on ML, one needs data of a certain sort, such as gene expression data or microarray data. To reduce the dataset's dimensionality, feature selection is proposed as an optimal solution to high dimensionality challenges and to deal with microarray data, this research work aims to perform the 2-stage feature selection. In the initial stage, the Particle Swarm Optimization (PSO) and Bare-bone PSO (BBPSO) are applied to the dataset separately. Then the common features selected by PSO and BBPSO are considered. Then Levy Flight Moth Flame Optimization (LFMFO) is applied to choose the final optimal set of features. Basic existing ML classifiers are used for the first prediction. Afterwards, the Majority Voting technique is applied to develop the ensemble technique. The proposed model is developed over four Cancer microarray datasets, including CNS, Lung Cancer, Ovarian Cancer, and Breast Cancer. The experimental analysis presents the proposed model obtains the highest accuracy of 98.81% for the Ovarian Cancer dataset.

Image watermarking has developed as a prominent research area in the field of data protection. The authenticated data transmitted through the internet is not secure and can be pirated by unauthorized persons. To protect the valid data, Stationary Wavelet Transform (SWT), Discrete Wavelet Transform (DWT) and Singular Value Decomposition (SVD) based image watermarking algorithm is proposed in the hybrid domain. Initially the original and watermark images are decomposed into approximate (A), vertical (V), horizontal (H), and diagonal subbands (D) using SWT. The approximate band (A) is further decomposed into LL and detail (LH, HL, and HH) subbands using DWT. We calculated SVD for LL and HH subbands of original and watermark images to get the singular values. The singular values of the LL and HH subbands are modified to get the watermarked image. The performance of the proposed model is tested on a standard image dataset. The imperceptibility is evaluated using Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Feature Similarity Index (FSIM) metrics, and the robustness is validated based on the effective extraction of watermarks from the attacked watermarked image in terms of Normalized Cross Correlation (NCC).

This study introduces a robust framework for enhancing Content-Based Image Retrieval (CBIR) systems through the integration of supervised and unsupervised machine learning algorithms. Supervised learning algorithms, such as K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Linear Discriminant Analysis (LDA), and ensemble methods like Bagging and AdaBoost, are used with unsupervised learning techniques, including K-Means and K-Medoids clustering to improve the performance of CBIR. The core of the framework leverages advanced feature extraction methods, specifically ResNet-HOG Visual Word Fusion (RVWF) and ResNet-HOG Feature Fusion (RHFF), which utilize ResNet-50 for capturing high-level semantic information and Histogram of Oriented Gradients (HOG) for detailed texture analysis. A comparison was made between the similarity-based CBIR (standalone CBIR), classification-based CBIR, and clustering-based CBIR methods. The findings reveal that classification-based CBIR methods are superior to standalone and clustering-based CBIR methods in terms of retrieval accuracy and semantic interpretation. The proposed methods outperformed the state-of-the-art methods for different databases used in this study. The proposed frameworks demonstrated superior performance across multiple databases, including VisTex, Brodatz, Corel 10K, and Corel 1K. In the VisTex database, clustering using K-Medoids-based RVWF increased performance from 98.75% to 99.52%, while classification methods like Linear Discriminant or Bagging-based RVWF achieved 100% accuracy. Similarly, in the Brodatz database, K-Medoids-based RVWF clustering improved accuracy from 97.62% to 99.62%, with classification methods such as AdaBoost or Bagging-based RVWF reaching up to 100% accuracy. For the Corel 1K and Corel 10K databases, K-Medoids-based RVWF clustering enhanced results to 95.61% and 99.20% for RVW, respectively, while classification methods further increased accuracy to 98.20% for Corel 1K and 100% for Corel 10K. These results show that combining advanced feature extraction with machine learning algorithms can improve the performance of CBIR systems. CBIR based on clustering proved to outperform standalone CBIR systems, while classification-based CBIR systems offered the best results, making them the most suitable for accurate image retrieval.